MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
MambaX-Net is a dual-input network designed for longitudinal MRI segmentation, addressing limitations in traditional models that fail to utilize sequential patient data. The architecture uses Mamba and a Shape Extractor Module to leverage previous scan information, resulting in superior boundary precision and efficiency. It provides a robust foundation for automated clinical decision support in prostate cancer management.